CountDiffusion: Text-to-Image Synthesis with Training-Free Counting-Guidance Diffusion
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912364473876480 |
|---|---|
| author | Li, Yanyu Wan, Pencheng Han, Liang Wang, Yaowei Nie, Liqiang Zhang, Min |
| author_facet | Li, Yanyu Wan, Pencheng Han, Liang Wang, Yaowei Nie, Liqiang Zhang, Min |
| contents | Stable Diffusion has advanced text-to-image synthesis, but training models to generate images with accurate object quantity is still difficult due to the high computational cost and the challenge of teaching models the abstract concept of quantity. In this paper, we propose CountDiffusion, a training-free framework aiming at generating images with correct object quantity from textual descriptions. CountDiffusion consists of two stages. In the first stage, an intermediate denoising result is generated by the diffusion model to predict the final synthesized image with one-step denoising, and a counting model is used to count the number of objects in this image. In the second stage, a correction module is used to correct the object quantity by changing the attention map of the object with universal guidance. The proposed CountDiffusion can be plugged into any diffusion-based text-to-image (T2I) generation models without further training. Experiment results demonstrate the superiority of our proposed CountDiffusion, which improves the accurate object quantity generation ability of T2I models by a large margin. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_04347 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CountDiffusion: Text-to-Image Synthesis with Training-Free Counting-Guidance Diffusion Li, Yanyu Wan, Pencheng Han, Liang Wang, Yaowei Nie, Liqiang Zhang, Min Computer Vision and Pattern Recognition Stable Diffusion has advanced text-to-image synthesis, but training models to generate images with accurate object quantity is still difficult due to the high computational cost and the challenge of teaching models the abstract concept of quantity. In this paper, we propose CountDiffusion, a training-free framework aiming at generating images with correct object quantity from textual descriptions. CountDiffusion consists of two stages. In the first stage, an intermediate denoising result is generated by the diffusion model to predict the final synthesized image with one-step denoising, and a counting model is used to count the number of objects in this image. In the second stage, a correction module is used to correct the object quantity by changing the attention map of the object with universal guidance. The proposed CountDiffusion can be plugged into any diffusion-based text-to-image (T2I) generation models without further training. Experiment results demonstrate the superiority of our proposed CountDiffusion, which improves the accurate object quantity generation ability of T2I models by a large margin. |
| title | CountDiffusion: Text-to-Image Synthesis with Training-Free Counting-Guidance Diffusion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.04347 |